Research Outputs
Is news really pessimistic? Sentiment Analysis of Chilean online newspaper headlines
Objectives: This paper explores the popular belief that all news is bad news. Many claim not to read newspapers to avoid knowing about the worst of our society. We want tear down the myth by applying a Sentiment Analysis (SA) approach. Method/Analysis: This work applies sentiment analysis techniques to study the headline bias of online newspapers for the period between March 2014 and April 2015. We analyzed 2953 headlines gathered from five of the most popular Chilean newspapers which are available online and offer RSS feeds. Findings: Our results show a roughly equivalent percentage of positive bias (38%) and negative bias (37%) instances, with 25% of headlines exhibiting a neutral bias. Automatic classification performance is promising, with decent classifier performance and sensitivity, with plenty of room for improvement. Novelty/Improvement: This work also a domain-specific Spanish language tagged corpus was generated as a result of this work, which is a valuable resource for future studies.
Improving the affective analysis in texts. Automatic method to detect affective intensity in lexicons based on Plutchik’s wheel of emotions
Purpose: This paper aims to propose a method for automatically labelling an affective lexicon with intensity values by using the WordNet Similarity (WS) software package with the purpose of improving the results of an affective analysis process, which is relevant to interpreting the textual information that is available in social networks. The hypothesis states that it is possible to improve affective analysis by using a lexicon that is enriched with the intensity values obtained from similarity metrics. Encouraging results were obtained when an affective analysis based on a labelled lexicon was compared with that based on another lexicon without intensity values. Design/methodology/approach: The authors propose a method for the automatic extraction of the affective intensity values of words using the similarity metrics implemented in WS. First, the intensity values were calculated for words having an affective root in WordNet. Then, to evaluate the effectiveness of the proposal, the results of the affective analysis based on a labelled lexicon were compared to the results of an analysis with and without affective intensity values. Findings: The main contribution of this research is a method for the automatic extraction of the intensity values of affective words used to enrich a lexicon compared with the manual labelling process. The results obtained from the affective analysis with the new lexicon are encouraging, as they provide a better performance than those achieved using a lexicon without affective intensity values. Research limitations/implications: Given the restrictions for calculating the similarity between two words, the lexicon labelled with intensity values is a subset of the original lexicon, which means that a large proportion of the words in the corpus are not labelled in the new lexicon. Practical implications: The practical implications of this work include providing tools to improve the analysis of the feelings of the users of social networks. In particular, it is of interest to provide an affective lexicon that improves attempts to solve the problems of a digital society, such as the detection of cyberbullying. In this case, by achieving greater precision in the detection of emotions, it is possible to detect the roles of participants in a situation of cyberbullying, for example, the bully and victim. Other problems in which the application of affective lexicons is of importance are the detection of aggressiveness against women or gender violence or the detection of depressive states in young people and children. Social implications: This work is interested in providing an affective lexicon that improves attempts to solve the problems of a digital society, such as the detection of cyberbullying. In this case, by achieving greater precision in the detection of emotions, it is possible to detect the roles of participants in a situation of cyber bullying, for example, the bully and victim. Other problems in which the application of affective lexicons is of importance are the detection of aggressiveness against women or gender violence or the detection of depressive states in young people and children. Originality/value: The originality of the research lies in the proposed method for automatically labelling the words of an affective lexicon with intensity values by using WS. To date, a lexicon labelled with intensity values has been constructed using the opinions of experts, but that method is more expensive and requires more time than other existing methods. On the other hand, the new method developed herein is applicable to larger lexicons, requires less time and facilitates automatic updating.
Towards a holistic model for quality of learning object repositories: A practical application to the indicator of metadata compliance
Purpose: This paper aims to address the need to ensure the quality of metadata records describing learning resources. We propose improvements to a metadata-quality model, specifically for the compliance sub-feature of the functionality feature. Compliance is defined as adherence level of the learning object metadata content to the metadata standard used for its specification. The paper proposes metrics to assess the compliance, which are applied to a set of learning objects, showing their applicability and usefulness in activities related to resources management. Design/methodology/approach: The methodology considers a first stage of metrics refinement to obtain the indicator of the sub-feature compliance. The next stage is the proposal evaluation, where it is determined if metrics can be used as a conformity indicator of learning object metadata with a standard (metadata compliance). The usefulness of this indicator in the information retrieval area is approached through an assessment of learning objects where the quality level of its metadata and the ranking in which they are retrieved by a repository are correlated. Findings: This study confirmed that the best results for metrics of standardization, completeness, congruence, coherence, correctness and understandability, which determine the compliance indicator, were obtained for learning objects whose metadata were better labelled. Moreover, it was found that the learning objects with the highest level of compliance indicator have better positions in the ranking when a repository retrieves them through an exact search based on metadata. Research limitations/implications: In this study, only a sub-feature of the quality model is detailed, specifically the compliance of learning object standard. Another limitation was the size of the learning objects set used in the experiment. Practical implications: This proposal is independent from any metadata standard and can be applied to improve processes associated with the management of learning objects in a repository-like retrieval and recommendation. Originality/value: The originality and value of this proposal are related to quality of learning object metadata considered from a holistic point of view through six metrics. These metrics quantify both technical and pedagogical aspects through automatic evaluation and supported by experts. In addition, the applicability of the indicator in recovery systems is shown, by example to be incorporated as an additional criterion in the learning object ranking.
How useful TutorBot+ is for teaching and learning in programming courses: A preliminary study
Objective: The objective of this paper is to present preliminary work on the development of an EduChatBot tool and the measurement of the effects of its use aimed at providing effective feedback to programming course students. This bot, hereinafter referred to as tutorBot+, was constructed based on chatGPT3.5 and is tasked with assisting and providing timely positive feedback to students in computer science programming courses at UCSC. Methods/Analysis: The proposed method consists of four stages: (1) Immersion in the feedback and Large Language Models (LLMs) topic; (2) Development of tutorBot+ prototypes in both non-conversational and conversational versions; (3) Experiment design; and (4) Intervention and evaluation. The first stage involves a literature review on feedback and learning, the use of intelligent tutors in the educational context, as well as the topics of LLMs and chatGPT. The second and third stages detail the development of tutorBot+ in its two versions, and the final stage lays the foundation for a quasi-experimental study involving students in the curriculum activities of Programming Workshop and Database Workshop, focusing on learning outcomes related to the development of computational thinking skills, and facilitating the use and measurement of the tool’s effects. Findings: The preliminary results of this work are promising, as two functional prototypes of tutorBot+ have been developed for both the non-conversational and conversational versions. Additionally, there is ongoing exploration into the possibility of creating a domain-specific model based on pretrained models for programming, integrating tutorBot+ with other platforms, and designing an experiment to measure student performance, motivation, and the tool’s effectiveness.
Teach me to play, gamer! Imitative learning in computer games via linguistic description of complex phenomena and decision trees
In this article, we present a new machine learning model by imitation based on the linguistic description of complex phenomena. The idea consists of, first, capturing the behaviour of human players by creating a computational perception network based on the execution traces of the games and, second, representing it using fuzzy logic (linguistic variables and if-then rules). From this knowledge, a set of data (dataset) is automatically created to generate a learning model based on decision trees. This model will be used later to automatically control the movements of a bot. The result is an artificial agent that mimics the human player. We have implemented, tested and evaluated this technology from two different points of view: performance by using classical metrics (accuracy, ROC area and PRC area) and believability by using a Turing test for trained bots. The results obtained are interesting and promising, showing that this method can be a good alternative to design and implement the behaviour of intelligent agents in video game development.
What do our Children read about? Affect analysis of Chilean school texts
We present a study of the affective character of 1st to 8th year Chilean school texts, to which we applied lexicon-based affect analysis techniques to identify 6 basic emotions (anger, sadness, fear, disgust, surprise and happiness). First, we generated a corpus of 525 documents, 18176 paragraphs and 137516 words. Then, using the affective words frequency, we built a classifier based on Emotion Word Density to detect emotions in the texts. Our results show that the predominant affective states are happiness (58%), sadness (16%) and fear (12%). The 6 basic emotions are present in most literary forms with uniform relative density except for songs, where anger is absent. Classifier performance was validated by comparing its results against the opinions of experts in the field, and its results show an above-average conformity (accuracy = 63%), above-average predictive capacity (precision = 69%) and good classifier sensitivity (recall = 80% and f-measure = 93%).
The role of WordNet similarity in the affective analysis pipeline
Sentiment Analysis (SA) is a useful and important discipline in Computer Science, as it allows having a knowledge base about the opinions of people regarding a topic. This knowledge is used to improve decision-making processes. One approach to achieve this is based on the use of lexical knowledge structures. In particular, our aim is to enrich an affective lexicon by the analysis of the similarity relationship between words. The hypothesis of this work states that the similarities of the words belonging to an affective category, with respect to any other word, behave in a homogeneous way within each affective category. The experimental results show that words of a same affective category have a homogeneous similarity with an antonym, and that the similarities of these words with any of their antonyms have a low variability. The novelty of this paper is that it builds the bases of a mechanism that allows incorporating the intensity in an affective lexicon automatically.
Detecting aggressiveness in tweets: A hybrid model for detecting cyberbullying in the Spanish language
In recent years, the use of social networks has increased exponentially, which has led to a significant increase in cyberbullying. Currently, in the field of Computer Science, research has been made on how to detect aggressiveness in texts, which is a prelude to detecting cyberbullying. In this field, the main work has been done for English language texts, mainly using Machine Learning (ML) approaches, Lexicon approaches to a lesser extent, and very few works using hybrid approaches. In these, Lexicons and Machine Learning algorithms are used, such as counting the number of bad words in a sentence using a Lexicon of bad words, which serves as an input feature for classification algorithms. This research aims at contributing towards detecting aggressiveness in Spanish language texts by creating different models that combine the Lexicons and ML approach. Twenty-two models that combine techniques and algorithms from both approaches are proposed, and for their application, certain hyperparameters are adjusted in the training datasets of the corpora, to obtain the best results in the test datasets. Three Spanish language corpora are used in the evaluation: Chilean, Mexican, and Chilean-Mexican corpora. The results indicate that hybrid models obtain the best results in the 3 corpora, over implemented models that do not use Lexicons. This shows that by mixing approaches, aggressiveness detection improves. Finally, a web application is developed that gives applicability to each model by classifying tweets, allowing evaluating the performance of models with external corpus and receiving feedback on the prediction of each one for future research. In addition, an API is available that can be integrated into technological tools for parental control, online plugins for writing analysis in social networks, and educational tools, among others.
Explainable Hopfield Neural Networks using an automatic video-generation system
Hopfield Neural Networks (HNNs) are recurrent neural networks used to implement associative memory. They can be applied to pattern recognition, optimization, or image segmentation. However, sometimes it is not easy to provide the users with good explanations about the results obtained with them due to mainly the large number of changes in the state of neurons (and their weights) produced during a problem of machine learning. There are currently limited techniques to visualize, verbalize, or abstract HNNs. This paper outlines how we can construct automatic video-generation systems to explain its execution. This work constitutes a novel approach to obtain explainable artificial intelligence systems in general and HNNs in particular building on the theory of data-to-text systems and software visualization approaches. We present a complete methodology to build these kinds of systems. Software architecture is also designed, implemented, and tested. Technical details about the implementation are also detailed and explained. We apply our approach to creating a complete explainer video about the execution of HNNs on a small recognition problem. Finally, several aspects of the videos generated are evaluated (quality, content, motivation and design/presentation).
Predicting engineering undergraduates dropout: A case study in Chile
The main objective of this article is to present and validate a statistical model (N = 3,152) to predict the dropout of students from the School of Engineering of the Universidad CatĂ³lica de la SantĂsima ConcepciĂ³n (UCSC) in Chile. Student droupout in engineering is a generalized and multifactorial phenomenon, even more so when the student can use his or her university access score for a period of two years. In the UCSC, a distinction is made between formal and nonformal droupout. The information collection methodology in this study included the survey administered by the Department of Evaluation, Measurement and Educational Registry of Chile (DEMRE) and input from the Directorate of Admission and Academic Registration of the UCSC. Within the analysis groups were students who formally resigned and were analyzed according to the reasons they gave for leaving; the other group was constituted by students who did not formalize their abandonment, deserters. Subsequently, a logistic regression analysis was applied to determine which variables would best explain the phenomenon of droupout. Among the main factors are gender (GENDER), program (AU), cumulative average score (PPA_SCORE), mathematics score of the university selection test (PSU_MATH_SCORE), mother education level (EDU_MOM), progression rate of student in engineering program (PROGRESSION_RATE) and socioeconomic quintile of student (QUINTILE). The performance of the prediction model shows an accuracy (88.53%) and precision (88.69%), which is a very encouraging result in relation to the performance of the studies reviewed in the literature.